Inductive knowledge graph completion
11 papers with code • 3 benchmarks • 0 datasets
The dominant paradigm for relation prediction in knowledge graphs involves learning and operating on latent representations (i. e., embeddings) of entities and relations.
Logical rules are a popular knowledge representation language in many domains, representing background knowledge and encoding information that can be derived from given facts in a compact form.
Despite the importance of inductive link prediction, most previous works focused on transductive link prediction and cannot manage previously unseen entities.
Many systems have been developed in recent years to mine logical rules from large-scale Knowledge Graphs (KGs), on the grounds that representing regularities as rules enables both the interpretable inference of new facts, and the explanation of known facts.
In this paper, we propose an INductive knowledge GRAph eMbedding method, InGram, that can generate embeddings of new relations as well as new entities at inference time.
The task of inductive knowledge graph completion requires models to learn inference patterns from a training graph, which can then be used to make predictions on a disjoint test graph.